您正在浏览:主页 > 游戏新闻 > 【超全】CVPR 2018 收录论文所有标题列表
作者：雷霆之怒公益服 来源：http://www.edmi.com.cn 时间：2018-09-09 09:45
An Analysis of Scale Invariance in Object Detection - SNIP
上面简单介绍了 CVPR ，其重要性不言而喻。而本文的重点，也是各位童鞋关注的焦点就在于 CVPR 2018。我们先看一组数据：979/3303 ~= 29.6%，该数据是指 CVPR 2018 论文的收录比。
Residual Dense Network for Image Super-Resolution
Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification
Neural Baby Talk
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
Context-aware Synthesis for Video Frame Interpolation
Recurrent Pixel Embedding for Instance Grouping
Real-world Anomaly Detection in Surveillance Videos
打开最上面的链接，一般就可以成功跳转至 arXiv 的论文下载界面
Improving Color Reproduction Accuracy in the Camera Imaging Pipeline
Non-local Neural Networks
Single-Shot Refinement Neural Network for Object Detection
Learning Intrinsic Image Decomposition from Watching the World
Semi-parametric Image Synthesis
link:
A Two-Step Disentanglement Method
DensePose: Multi-Person Dense Human Pose Estimation In The Wild
Learning to Sketch with Shortcut Cycle Consistency
Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspective
Recovering Realistic Texture in Image Super-resolution by Spatial Feature Modulation
PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
Illuminant Spectra-based Source Separation Using Flash Photography
SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
本文将介绍 CVPR 2018 所有录用论文的标题, 包括每篇论文属于 oral, spotlight 还是 poster 的情况。大家可以根据论文的标题去 google/baidu，即可以找到相关 pdf/github/homepage 链接。
Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks
温馨提示：CVPR 2018 大会将于 2018 年 6 月 18~22 日于美国犹他州的盐湖城（Salt Lake City）举办。
Few-Shot Image Recognition by Predicting Parameters from Activations
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
Boosting Self-Supervised Learning via Knowledge Transfer
Decorrelated Batch Normalization
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds
Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
Attend and Interact: Higher-Order Object Interactions for Video Understanding
Easy Identification from Better Constraints: Multi-Shot Person Re-Identification from Reference Constraints
TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays
Im2Flow: Motion Hallucination from Static Images for Action Recognition
Image Generation from Scene Graphs
Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
COCO-Stuff: Thing and Stuff Classes in Context
Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification
4D Human Body Correspondences from Panoramic Depth Maps
Objects as context for detecting their semantic parts
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Look at Boundary: A Boundary-Aware Face Alignment Algorithm
SfSNet : Learning Shape, Reflectance and Illuminance of Faces `in the wild'
Semantic Visual Localization
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
Video Representation Learning Using Discriminative Pooling
Functional Map of the World
Shape from Shading through Shape Evolution
Mask-guided Contrastive Attention Model for Person Re-Identification
Frustum PointNets for 3D Object Detection from RGB-D Data
PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning
Learning a Toolchain for Image Restoration
Recognizing Human Actions as Evolution of Pose Estimation Maps
Rethinking the Faster R-CNN Architecture for Temporal Action Localization
Tell Me Where To Look: Guided Attention Inference Network
Motion-Guided Cascaded Refinement Network for Video Object Segmentation
MapNet: Geometry-Aware Learning of Maps for Camera Localization
VITAL: VIsual Tracking via Adversarial Learning
SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-rigid Motion
CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation
Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
A Benchmark for Articulated Human Pose Estimation and Tracking
Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration
Multi-Cue Correlation Filters for Robust Visual Tracking
Deep Layer Aggregation
Deep Cross-media Knowledge Transfer
Referring Relationships
Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment
Generative Non-Rigid Shape Completion with Graph Convolutional Autoencoders
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
Generative Adversarial Learning Towards Fast Weakly Supervised Detection
Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation
LSTM stack-based Neural Multi-sequence Alignment TeCHnique (NeuMATCH)
Single Image Reflection Separation with Perceptual Losses
Weakly Supervised Instance Segmentation using Class Peak Response
Unsupervised CCA
Dynamic Video Segmentation Network
Unsupervised Deep Generative Adversarial Hashing Network
Video Rain Removal By Multiscale Convolutional Sparse Coding
Context-aware Deep Feature Compression for High-speed Visual Tracking
Context Encoding for Semantic Segmentation
PU-Net: Point Cloud Upsampling Network
Fast and Accurate Online Video Object Segmentation via Tracking Parts
Min-Entropy Latent Model for Weakly Supervised Object Detection
Camera Style Adaptation for Person Re-identification
TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays
TOM-Net: Learning Transparent Object Matting from a Single Image
Memory Matching Networks for One-Shot Image Recognition
Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation
CVPR 2018 Accepted Papers
Cube Padding for Weakly-Supervised Saliency Prediction in 360$^{circ}$ Videos
pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment
Hashing as Tie-Aware Learning to Rank
Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB
Densely Connected Pyramid Dehazing Network
Learning a Discriminative Prior for Blind Image Deblurring
3D Hand Pose Estimation: From Current Achievements to Future Goals
Generative Image Inpainting with Contextual Attention
Low-shot Learning from Imaginary Data
Left-Right Comparative Recurrent Model for Stereo Matching
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning
A Variational U-Net for Conditional Appearance and Shape Generation
Scalable and Effective Deep CCA via Soft Decorrelation
Stereoscopic Neural Style Transfer
Learning to Find Good Correspondences
Kernelized Subspace Pooling for Deep Local Deors
A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds
Left/Right Asymmetric Layer Skippable Networks
Unsupervised Learning of Depth and Egomotion from Monocular Video Using 3D Geometric Constraints
Crowd Counting with Deep Negative Correlation Learning
Dynamic-Structured Semantic Propagation Network
Visual Question Generation as Dual Task of Visual Question Answering
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
Cross-Domain Self-supervised Multi-task Feature Learning Using Synthetic Game Imagery
Weakly-supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation
Face Aging with Identity-Preserved Conditional Generative Adversarial Networks
PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
Weakly Supervised Instance Segmentation using Class Peak Response
Finding Tiny Faces in the Wild with Generative Adversarial Network
Squeeze-and-Excitation Networks
End-to-end Recovery of Human Shape and Pose
授人以鱼，不如授人以鱼。上述只是 Amusi 常用小技巧，真的关公面前舞大刀了，大家可以自由发挥~
Optimizing Local Feature Deors for Nearest Neighbor Matching
Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs
Generating Synthetic X-ray Images of a Person from the Surface Geometry
Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
Textbook Question Answering under Teacher Guidance with Memory Networks
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
Deep Extreme Cut: From Extreme Points to Object Segmentation
Embodied Real-World Active Perception
Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
NAG: Network for Adversary Generation
Integrated facial landmark localization and super-resolution of real-world very low resolution faces in arbitrary poses with GANs
Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
Nonlinear 3D Face Morphable Model
Taskonomy: Disentangling Task Transfer Learning
Recognize Actions by Disentangling Components of Dynamics
Visual Question Generation as Dual Task of Visual Question Answering
DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems
Visual Question Reasoning on General Dependency Tree
Probabilistic Plant Modeling via Multi-View Image-to-Image Translation
Five-point Fundamental Matrix Estimation for Uncalibrated Cameras
Automatic 3D Indoor Scene Modeling from Single Panorama
VITON: An Image-based Virtual Try-on Network
Density-aware Single Image De-raining using a Multi-stream Dense Network
CVPR 2018论文列表
DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map
Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
Deep Group-shuffling Random Walk for Person Re-identification
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking
Reconstructing Thin Structures of Manifold Surfaces by Integrating Spatial Curves
Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
Disentangling Structure and Aesthetics for Content-aware Image Completion
Facelet-Bank for Fast Portrait Manipulation
Who Let The Dogs Out? Modeling Dog Behavior From Visual Data
Classification Driven Dynamic Image Enhancement
Deep Mutual Learning
NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning
Improved Human Pose Estimation through Adversarial Data Augmentation
Towards Effective Low-bitwidth Convolutional Neural Networks
UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
Learning from Millions of 3D Scans for Large-scale 3D Face Recognition
Dynamic Zoom-in Network for Fast Object Detection in Large Images
Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
Pseudo-Mask Augmented Object Detection
Transductive Unbiased Embedding for Zero-Shot Learning
Human Pose Estimation with Parsing Induced Learner
Learning to Hash by Discrepancy Minimization
Efficient Diverse Ensemble for Discriminative Co-Tracking
Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
One-shot Action Localization by Sequence Matching Network
Learning to Find Good Correspondences
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
Practical Block-wise Neural Network Architecture Generation
CVPR 是 IEEE Conference on Computer Vision and Pattern Recognition 的缩写，即 IEEE 国际计算机视觉与模式识别会议。该会议是由 IEEE 举办的计算机视觉和模式识别领域的顶级会议。
HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification
NISP: Pruning Networks using Neuron Importance Score Propagation
Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks
FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds
Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification
Learning from the Deep: A Revised Underwater Image Formation Model
Amusi 已经将 CVPR 2018 所有论文清单上传到 daily-paper-computer-vision 上，大家直接点击文末的 “阅读全文”，即可访问 daily-paper-computer-vision，下载 cvpr2018-paper-list.csv。
3D Human Pose Estimation in the Wild by Adversarial Learning
Optimizing Video Object Detection via a Scale-Time Lattice
Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
An Analysis of Scale Invariance in Object Detection - SNIP
Learning to Detect Features in Texture Images
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
On the Importance of Label Quality for Semantic Segmentation
Answer with Grounding Snippets: Focal Visual-Text Attention for Visual Question Answering
Deep Cross-media Knowledge Transfer
SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
Attention-aware Compositional Network for Person Re-Identification
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
Zero-Shot Sketch-Image Hashing
Deep Layer Aggregation
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Detecting and Recognizing Human-Object Interactions
SINT++: Robust Visual Tracking via Adversarial Hard Positive Generation
Duplex Generative Adversarial Network for Unsupervised Domain Adaptation
Recurrent Scene Parsing with Perspective Understanding in the Loop
Learning Dual Convolutional Neural Networks for Low-Level Vision
Low-Latency Video Semantic Segmentation
Detect-and-Track: Efficient Pose Estimation in Videos
Finding Tiny Faces in the Wild with Generative Adversarial Network
Automatic 3D Indoor Scene Modeling from Single Panorama
Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
Style Aggregated Network for Facial Landmark Detection
Video Person Re-identification with Competitive Snippet-similarity Aggregation and Co-attentive Snippet Embedding
Harmonious Attention Network for Person Re-Identication
Residual Parameter Transfer for Deep Domain Adaptation
From Lifestyle VLOGs to Everyday Interactions
Excitation Backprop for RNNs
Future Frame Prediction for Anomaly Detection A New Baseline
Pose-Guided Photorealistic Face Rotation
Tangent Convolutions for Dense Prediction in 3D
Tracking Multiple Objects Outside the Line of Sight using Speckle Imaging
Lean Multiclass Crowdsourcing
Efficient Subpixel Refinement with Symbolic Linear Predictors
Tell Me Where To Look: Guided Attention Inference Network
3D-RCNN: Instance-level 3D Scene Understanding via Render-and-Compare
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
Improving Object Localization with Fitness NMS and Bounded IoU Loss
Graph-Cut RANSAC
Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning
由于微信字数限制，没有全部显示，详细 list 请查看 Amusi 整理的
On the Robustness of Semantic Segmentation Models to Adversarial Attacks
Feature Quantization for Defending Against Distortion of Images
【新智元导读】计算机视觉最具影响力的学术会议之一的 IEEE CVPR 将于 2018 年 6 月 18 日 - 22 日在美国盐湖城召开举行。据 CVPR 官网显示，今年大会有超过 3300 篇论文投稿，其中录取 979 篇；相比去年 783 篇论文，今年增长了近 25%。本文将介绍 CVPR 2018 所有录用论文的标题, 包括每篇论文属于 oral, spotlight 还是 poster 的情况。
Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer
A Fast Resection-Intersection Method for the Known Rotation Problem
Domain Adaptive Faster R-CNN for Object Detection in the Wild
Single-Shot Object Detection with Enriched Semantics
Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene
SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-rigid Motion
Imagination-IQA: No-reference Image Quality Assessment via Adversarial Learning
Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
Unsupervised Training for 3D Morphable Model Regression
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Deep Adversarial Metric Learning
3D Hand Pose Estimation: From Current Achievements to Future Goals
Discovering Point Lights with Intensity Distance Fields
DensePose: Multi-Person Dense Human Pose Estimation In The Wild
Taskonomy: Disentangling Task Transfer Learning
GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition
Coupled End-to-end Transfer Learning with Generalized Fisher Information
Real-World Repetition Estimation by Div, Grad and Curl
Instance Embedding Transfer to Unsupervised Video Object Segmentation
Deep End-to-End Time-of-Flight Imaging
Neural Baby Talk
Few-Shot Image Recognition by Predicting Parameters from Activations
Reflection Removal for Large-Scale 3D Point Clouds
Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints
Augmenting Crowd-Sourced 3D Reconstructions using Semantic Detections
Generating Synthetic X-ray Images of a Person from the Surface Geometry
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
link:
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
Unsupervised Textual Grounding: Linking Words to Image Concepts
IQA: Visual Question Answering in Interactive Environments
Zero-Shot Sketch-Image Hashing
Repulsion Loss: Detecting Pedestrians in a Crowd
3D Object Detection with Latent Support Surfaces
Tangent Convolutions for Dense Prediction in 3D
Multiple Granularity Group Interaction Prediction
A Variational U-Net for Conditional Appearance and Shape Generation
BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation
Nonlinear 3D Face Morphable Model
W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection
Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
Scale-recurrent Network for Deep Image Deblurring
Functional Map of the World
High-order tensor regularization with application to attribute ranking
TOM-Net: Learning Transparent Object Matting from a Single Image
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
Learning a Discriminative Feature Network for Semantic Segmentation
Exploit the Unknown Gradually:~ One-Shot Video-Based Person Re-Identification by Stepwise Learning
Illuminant Spectra-based Source Separation Using Flash Photography
HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN
Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Dense 3D Regression for Hand Pose Estimation
Consensus Maximization for Semantic Region Correspondences
之前在知乎和各个新闻平台上都看到了 CVPR 2018 list，，但都是一组纯序号，既没有属性也没有论文标题。机（wu）智（nai）的童鞋也只能去 arXiv 上 follow 最新的 paper，如果能遇见带有 CVPR 2018 标志的 paper，相信内心还有点小激动呢。
Hyperparameter Optimization for Tracking with Continuous Deep Q-Learning
PointGrid: A Deep Network for 3D Shape Understanding
M3: Multimodal Memory Modelling for Video Captioning
然后将需要阅读的论文标题复制到 google/baidu 搜索框中，比如《An Analysis of Scale Invariance in Object Detection - SNIP》
Deep Regression Forests for Age Estimation
Actor and Action Video Segmentation from a Sentence
Monocular Relative Depth Perception with Web Stereo Data Supervision
https://github.com/amusi/daily-paper-computer-vision/blob/master/2018/cvpr2018-paper-list.csv
Left-Right Comparative Recurrent Model for Stereo Matching
Learning a Toolchain for Image Restoration
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
Unsupervised Deep Generative Adversarial Hashing Network
Learning to Adapt Structured Output Space for Semantic Segmentation
Low-shot Learning from Imaginary Data
Embodied Question Answering
Interactive Image Segmentation with Latent Diversity
End-to-end Flow Correlation Tracking with Spatial-temporal Attention
Low-Shot Recognition with Imprinted Weights
Learning Convolutional Networks for Content-weighted Image Compression
MegDet: A Large Mini-Batch Object Detector
Imagine it for me: Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts
Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning
BlockDrop: Dynamic Inference Paths in Residual Networks
Hand PointNet: 3D Hand Pose Estimation using Point Sets
Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network
Beyond Trade-off: Accelerate FCN-based Face Detection with Higher Accuracy
CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles
Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatio-temporal Patterns
Learning by Asking Questions
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
Thoracic Disease Identification and Localization with Limited Supervision
CSGNet: Neural Shape Parser for Constructive Solid Geometry
Learning to Adapt Structured Output Space for Semantic Segmentation
Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
Rotation Averaging and Strong Duality
Missing Slice Recovery for Tensors Using a Low-rank Model in Embedded Space
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
SurfConv: Bridging 3D and 2D Convolution for RGBD Images
A High-Quality Denoising Dataset for Smartphone Cameras
ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
Sparse, Smart Contours to Represent and Edit Images
Seeing Temporal Modulation of Lights from Standard Cameras
Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification
End-to-end weakly-supervised semantic alignment
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
MatNet: Modular Attention Network for Referring Expression Comprehension
有了论文标题，真的就可以为所欲为~
Lean Multiclass Crowdsourcing
Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation
Every Smile is Unique: Landmark-guided Diverse Smile Generation
Interleaved Structured Sparse Convolutional Neural Networks
DoubleFusion: Real-time Capture of Human Performance with Inner Body Shape from a Single Depth Sensor
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Fast Video Object Segmentation by Reference-Guided Mask Propagation
Attentional ShapeContextNet for Point Cloud Recognition
Gated Fusion Network for Single Image Dehazing
LSTM stack-based Neural Multi-sequence Alignment TeCHnique (NeuMATCH)
Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
Deep Material-aware Cross-spectral Stereo Matching
Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
Unsupervised Discovery of Object Landmarks as Structural Representations
MegDet: A Large Mini-Batch Object Detector
Tagging Like Humans: Diverse and Distinct Image Annotation
Separating Self-Expression and Visual Content in Hashtag Supervision
Iterative Visual Reasoning Beyond Convolutions
Real-World Repetition Estimation by Div, Grad and Curl
3D-RCNN: Instance-level 3D Scene Understanding via Render-and-Compare
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
Unsupervised Textual Grounding: Linking Words to Image Concepts
会议的主要内容是计算机视觉与模式识别技术。CVPR 是世界顶级的计算机视觉会议（三大顶会之一，另外两个是 ICCV 和 ECCV）。本会议每年都会有固定的研讨主题，而每一年都会有公司赞助该会议并获得在会场展示的机会。
Soccer on Your Tabletop
Iterative Visual Reasoning Beyond Convolutions
Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
SfSNet : Learning Shape, Reflectance and Illuminance of Faces `in the wild'
A Bi-directional Message Passing Model for Salient Object Detection
Integrated facial landmark localization and super-resolution of real-world very low resolution faces in arbitrary poses with GANs
Finding It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Video"
Detecting and Recognizing Human-Object Interactions
Human-centric Indoor Scene Synthesis Using Stochastic Grammar
Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks
Zigzag Learning for Weakly Supervised Object Detection
Video Captioning via Hierarchical Reinforcement Learning
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
Learning to Parse Wireframes in Images of Man-Made Environments
PointGrid: A Deep Network for 3D Shape Understanding
Visual Question Reasoning on General Dependency Tree
NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning
GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB
Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking
Multi-view Harmonized Bilinear Network for 3D Object Recognition
Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes
Interleaved Structured Sparse Convolutional Neural Networks
Frame-Recurrent Video Super-Resolution
CVPR 2018
Baseline Desensitizing In Translation Averaging
EPINET: A Fully-Convolutional Neural Network for Light Field Depth Estimation by Using Epipolar Geometry
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints
End-to-End Dense Video Captioning with Masked Transformer
Learning to Act Properly: Predicting and Explaining Affordances from Images
Semi-parametric Image Synthesis
In-Place Activated BatchNorm for Memory-Optimized Training of DNNs
Pose Transferrable Person Re-Identification
Improving Occlusion and Hard Negative Handling for Single-Stage Object Detectors
MoNet: Deep Motion Exploitation for Video Object Segmentation
Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
Viewpoint-aware Attentive Multi-view Inference for Vehicle Re-identification
Unifying Identification and Context Learning for Person Recognition
Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation
Dynamic Few-Shot Visual Learning without Forgetting
Demo2Vec: Reasoning Object Affordances from Online Videos
M3: Multimodal Memory Modelling for Video Captioning
Collaborative and Adversarial Network for Unsupervised domain adaptation
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection
MegaDepth: Learning Single-View Depth Prediction from Internet Photos
Towards Open-Set Identity Preserving Face Synthesis
Learning to Compare: Relation Network for Few-Shot Learning
Edit Probability for Scene Text Recognition
Actor and Action Video Segmentation from a Sentence
What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets
Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks
Audio to Body Dynamics
Fast and Accurate Online Video Object Segmentation via Tracking Parts
Finding It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Video"
Conditional Generative Adversarial Network for Structured Domain Adaptation
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
Learning Intrinsic Image Decomposition from Watching the World
Low-Latency Video Semantic Segmentation
What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets
Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation
Amusi 在对知识的不断追求中，发现了 CVPR 2018 所有收录论文的名单，既包含了序号，也包含了属性（oral、spotlight 或 poster）以及最最最重要的论文标题！
Audio to Body Dynamics
Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network
Visual Relationship Learning with a Factorization-based Prior
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
Scale-Transferrable Object Detection
CVPR 有着较为严苛的录用标准，会议整体的录取率通常不超过 30%，而口头报告的论文比例更是不高于 5%。而会议的组织方是一个循环的志愿群体，通常在某次会议召开的三年之前通过遴选产生。CVPR 的审稿一般是双盲的，也就是说会议的审稿与投稿方均不知道对方的信息。通常某一篇论文需要由三位审稿者进行审读。最后再由会议的领域主席 (area chair) 决定论文是否可被接收。
Learning to Detect Features in Texture Images
Efficient Video Object Segmentation via Network Modulation
Universal Denoising Networks : A Novel CNN-based Network Architecture for Image Denoising
Unsupervised Discovery of Object Landmarks as Structural Representations
VITAL: VIsual Tracking via Adversarial Learning
SSNet: Scale Selection Network for Online 3D Action Prediction
An End-to-End TextSpotter with Explicit Alignment and Attention
Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints
Feedback-prop: Convolutional Neural Network Inference under Partial Evidence
Fine-grained Video Captioning for Sports Narrative
Erase or Fill? Deep Joint Recurrent Rain Removal and Reconstruction in Videos
The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation
Hand PointNet: 3D Hand Pose Estimation using Point Sets
Deep Adversarial Metric Learning
Answer with Grounding Snippets: Focal Visual-Text Attention for Visual Question Answering
Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning
Squeeze-and-Excitation Networks
SSNet: Scale Selection Network for Online 3D Action Prediction
Enhancing the Spatial Resolution of Stereo Images using a Parallax Prior
Interpretable Convolutional Neural Networks
Rotation-sensitive Regression for Oriented Scene Text Detection
Textbook Question Answering under Teacher Guidance with Memory Networks
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
Revisiting Video Saliency: A Large-scale Benchmark and a New Model
Guided Proofreading of Automatic Segmentations for Connectomics
MapNet: Geometry-Aware Learning of Maps for Camera Localization
Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
Towards a Mathematical Understanding of the Difficulty in Learning with Feedforward Neural Networks
打开 cvpr2018-paper-list.csv，按下 crtl + F，输入要查找的内容，如 Object Detection，然后你就可以看到一篇篇关于 Object Detection 的论文啦！
CVPR 2018概览
End-to-End Deep Kronecker-Product Matching for Person Re-identification
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Fast Video Object Segmentation by Reference-Guided Mask Propagation
Point-wise Convolutional Neural Networks
Shape from Shading through Shape Evolution
A Face to Face Neural Conversation Model
Bootstrapping the Performance of Webly Supervised Semantic Segmentation
Residual Dense Network for Image Super-Resolution
Consensus Maximization for Semantic Region Correspondences
Fast End-to-End Trainable Guided Filter
Pose-Guided Photorealistic Face Rotation
Learning Superpixels with Segmentation-Aware Affinity Loss
Practical Block-wise Neural Network Architecture Generation
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations
Re-weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation
Context Encoding for Semantic Segmentation
Multi-Level Factorisation Net for Person Re-Identification
Embodied Real-World Active Perception
Learning Facial Action Units from Web Images with Scalable Weakly Supervised Clustering
Multi-view Harmonized Bilinear Network for 3D Object Recognition
Towards Pose Invariant Face Recognition in the Wild
Adversarial Complementary Learning for Weakly Supervised Object Localization
Deep Cauchy Hashing for Hamming Space Retrieval
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
Unsupervised Training for 3D Morphable Model Regression
Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries
Partial Transfer Learning with Selective Adversarial Networks
Joint Cuts and Matching of Partitions in One Graph
End-to-End Dense Video Captioning with Masked Transformer
DoubleFusion: Real-time Capture of Human Performance with Inner Body Shape from a Single Depth Sensor
Partial Transfer Learning with Selective Adversarial Networks
Tracking Multiple Objects Outside the Line of Sight using Speckle Imaging
Rotation Averaging and Strong Duality
Fast and Accurate Single Image Super-Resolution via Information Distillation Network
Visual Grounding via Accumulated Attention
Cascaded Pyramid Network for Multi-Person Pose Estimation
Learning Markov Clustering Networks for Scene Text Detection
A Biresolution Spectral framework for Product Quantization
BlockDrop: Dynamic Inference Paths in Residual Networks
Learning to Localize Sound Source in Visual Scenes
Recurrent Pixel Embedding for Instance Grouping
GroupCap: Group-based Image Captioning with Structured Relevance and Diversity Constraints
Fine-grained Video Captioning for Sports Narrative
Learning to Segment Every Thing
VITON: An Image-based Virtual Try-on Network
Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge
Structure Preserving Video Prediction
NISP: Pruning Networks using Neuron Importance Score Propagation
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
Interpretable Convolutional Neural Networks
Salient Object Detection Driven by Fixation Prediction
A Memory Network Approach for Story-based Temporal Summarization of 360?Videos
Progressive Attention Guided Recurrent Network for Salient Object Detection
Exploring Disentangled Feature Representation Beyond Face Identification
GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB
Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification
Deep Texture Manifold for Ground Terrain Recognition
Collaborative and Adversarial Network for Unsupervised domain adaptation
Perturbative Neural Networks: Rethinking Convolution in CNNs
Im2Flow: Motion Hallucination from Static Images for Action Recognition
<<上一篇：独乐乐不如众乐乐 盘点那些好玩的本地多人游戏 >>
<<下一篇：《雷霆之怒公益服：一人的正义》新人物截图公布 >>